--- type: "article" title: "I Broke Every Table Formatting Rule and Claude Didn't Care - Except for One" newsletter: "Joyce Stack" newsletter_handle: "joycestack" newsletter_url: "https://work.joycestack.com/" author: "Joyce Stack (@joycestack)" published: "2026-04-29T06:54:06.000Z" canonical_url: "https://work.joycestack.com/a/i-broke-every-table-formatting-rule-and-claude-didn-t-care-e" markdown_url: "https://work.joycestack.com/a/i-broke-every-table-formatting-rule-and-claude-didn-t-care-e.md" chat_url: "https://work.joycestack.com/a/i-broke-every-table-formatting-rule-and-claude-didn-t-care-e/chat" source_url: "https://preview.mailerlite.io/preview/2117849/emails/186060546978613221" body_source: "native" likes: 0 replies: 0 body_words: 823 --- # I Broke Every Table Formatting Rule and Claude Didn't Care - Except for One This week's AI rabbit hole was tabular data in markdown files. The following (imperfect) experiment was supposed to give me evidence for an AI markdown guide so I could draft a skill. I started with tables as I learned from [@dachary](https://dacharycarey.com) that tables tend to be more efficient than prose. My thinking was given a table the author is writing, a skill would provide format guidance and flags structural issues that would degrade agent comprehension. It's not a linter as such but an opinionated guide. **The question I had:** If I deliberately break the structure of a documentation table, does an AI agent extract the wrong values? **The experiment setup.** I set up a baseline table with 12 rows in a Markdown README file. The kind of table that exists in thousands of repos. I created six versions of the same table: - the healthy well structured baseline - headers removed - cells emptied - headers abbreviated to two letter codes - two tables merged into one - prosed stuffed into cells All experiments were run using Claude UI / Claude Sonnet 4.6. I ran each experiment in a new window three times so I had 18 result files. ![](https://storage.mlcdn.com/account_image/2117849/nzXwFjYjcXhBYd25JxU4ZPfrBBPPN831I1Cb8JCY.png) example table data **The deliberate ambiguity.** The table was designed so values are meaningless without context. 3000 appears twice - once as a port and once as a timeout. US and EU appear in different rows — one is a locale, one is a deployment region. Without headers, the agent has to figure out which is which. **What I expected.** I expected more failures. I expected that the removal of headers would most definitely be an issue. It wasn't. I expected the ambitious 3000 number to be an issue and that the merging of different tables would confuse it no end. **The extraction prompt.** I had Claude generate the prompt. Twelve questions, one extraction prompt, a couple of ground rules — use only what's in the document, no guessing, no filling in gaps from training data. Some questions were simple. What's the default port. Some needed filtering. Which variables are required. Some were designed to trip it up - two variables default to 3000, name both and explain the difference. Same prompt. Same questions. Six different versions of the table. Score the answers against a known answer key. "Did the same model design the test and take the test?" I hear you ask. The answer is yes, and that's a legitimate concern. **What actually happened.** Five of six variants scored 12/12. Only one defect moved the score: empty cells. When I removed the PORT default and the CMS_BASE_URL required flag, the agent reported incomplete answers. But it only said so because I told it to. The prompt explicitly instructed the model to report NOT FOUND rather than guess. A real agent working in your repository doesn't get that instruction. It gets "set up this project" and fills in the blanks from whatever it knows. **An empty cell in a controlled test produces an honest gap. An empty cell in a real Copilot session produces a confident guess you won't notice is wrong.** **My take aways.** I set out to write an AI guide for markdown tables. I ended up with one rule. Don't leave cells empty. Use a placeholder — `N/A`, `none`, `—` — whatever works. An empty cell is ambiguous to a human and invisible to an agent. A placeholder is a decision made visible. The other rules I had lined up - headers, full words rather than abbreviations, one concept per table, no prose in cells are all still good practice for humans. But Claude compensated for every structural defect I threw at it. I'm not going to dress those up as evidence-based AI guidance. Fill in your cells. That's what the data tells me. **Further reading** These studies informed the experiment. None tested documentation tables which is why I ran my own. The findings from these papers can't be extrapolated to Markdown. Still interesting insights. **Sui et al. (WSDM 2024)** — How LLMs process tables across six formats. Found structural cues like headers improve performance. My experiment didn't confirm this on Sonnet. [arxiv.org/abs/2305.13062](https://arxiv.org/abs/2305.13062) **Liu et al. (NAACL 2024)** — Broke table structure while holding format constant. Found performance dropped. The paper that most predicted my no-headers variant would fail. It didn't. [aclanthology.org/2024.naacl-long.26](https://aclanthology.org/2024.naacl-long.26) **MMTU (2025)** — 25 table tasks, 30,000+ questions. Models handle lookups well but struggle with reasoning across columns. My experiment only tested lookups. [cse.engin.umich.edu](http://cse.engin.umich.edu) **JTON / Zen Grid (2026)** — Tested 10 LLMs. Format preference was model-specific. No format won universally. [arxiv.org/abs/2604.05865](https://arxiv.org/abs/2604.05865) **ViTaB-A (2026)** — Models get right answers from tables but can't reliably point to which cell they read. [arxiv.org/abs/2602.15769](https://arxiv.org/abs/2602.15769) **Joyce Stack** Hove, Brighton United Kingdom You are receiving this email because you signed up at joycestack.com. If you no longer wish to receive emails from us, you can unsubscribe at any time. Unsubscribe [![Sent by MailerLite](https://assets.mlcdn.com/ml/logo/sent-by-mailerlite.png)](https://www.mailerlite.com) *** ## Discussion No replies yet.